CN113223677A - Doctor matching method and device for patient - Google Patents

Doctor matching method and device for patient Download PDF

Info

Publication number
CN113223677A
CN113223677A CN202010072681.8A CN202010072681A CN113223677A CN 113223677 A CN113223677 A CN 113223677A CN 202010072681 A CN202010072681 A CN 202010072681A CN 113223677 A CN113223677 A CN 113223677A
Authority
CN
China
Prior art keywords
doctor
patient
candidate
target
matching
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202010072681.8A
Other languages
Chinese (zh)
Inventor
郑毅
王喆锋
徐童
李丹
袁晶
怀宝兴
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
University of Science and Technology of China USTC
Huawei Technologies Co Ltd
Original Assignee
University of Science and Technology of China USTC
Huawei Technologies Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by University of Science and Technology of China USTC, Huawei Technologies Co Ltd filed Critical University of Science and Technology of China USTC
Priority to CN202010072681.8A priority Critical patent/CN113223677A/en
Publication of CN113223677A publication Critical patent/CN113223677A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
    • G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms

Landscapes

  • Business, Economics & Management (AREA)
  • General Business, Economics & Management (AREA)
  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Biomedical Technology (AREA)
  • Epidemiology (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Primary Health Care (AREA)
  • Public Health (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Abstract

The application discloses a doctor matching method and device for a patient, and belongs to the technical field of communication. The method comprises the following steps: the method comprises the steps of obtaining a symptom data set and a characteristic data set of a patient, wherein the symptom data set is used for reflecting abnormal states of the body of the patient caused by diseases, the characteristic data set is used for identifying the patient, and the characteristic data set comprises gender data and age data. And determining a doctor-patient matching coefficient of the patient and each candidate doctor in the candidate doctors according to the symptom data set and the characteristic data set, wherein the doctor-patient matching coefficient is used for reflecting the matching degree of the patient and the candidate doctors. And determining a target doctor for the patient to visit from a plurality of candidate doctors according to the doctor-patient matching coefficient of the patient and each candidate doctor. And outputting indication information for indicating the target doctor to visit the patient. The present application improves the accuracy of determining to see a doctor for a patient.

Description

Doctor matching method and device for patient
Technical Field
The present application relates to the field of communications technologies, and in particular, to a doctor matching method and apparatus for a patient.
Background
With the growing number of medical institutions and doctors, patients need to reserve doctors when they seek medical advice. The more adept the scheduled doctor is at seeing the disease suffered by the patient, the more the patient is cured; on the other hand, if the doctor who has made the appointment is less skilled in the disease from which the patient suffers, the probability that the patient is cured is smaller, and therefore, it is important to match the doctor who is appropriate for the patient at the time of the appointment.
The current procedure for a patient to reserve a doctor typically involves: the patient firstly judges the disease according to the symptom of the patient, then obtains the data of the disease which is provided by the medical institution and is favored by each doctor, then determines the doctor who is favored to see the disease according to the data, and then appoints the doctor to see the disease.
However, the doctor who visits the patient is determined by the patient in a manual manner, resulting in a less accurate way of determining the doctor to visit.
Disclosure of Invention
The application provides a doctor matching method and device for a patient, and the problem that accuracy of determining a doctor for seeing a doctor for the patient is low can be solved.
In a first aspect, a doctor matching method for a patient is provided, which can be applied to an electronic device. The electronic device acquires a symptom data set and a feature data set of a patient, wherein the symptom data set is used for reflecting an abnormal state of the body of the patient caused by diseases, the feature data set is used for identifying the patient, and the feature data set comprises gender data and age data. The electronic equipment determines a doctor-patient matching coefficient of the patient and each candidate doctor in the candidate doctors according to the symptom data set and the characteristic data set, wherein the doctor-patient matching coefficient is used for reflecting the matching degree of the patient and the candidate doctors. The electronic equipment determines a target doctor for the patient to visit from a plurality of candidate doctors according to the doctor-patient matching coefficient of the patient and each candidate doctor. The electronic device outputs instruction information for instructing the target doctor to visit the patient.
Since the feature data set at least comprises gender data and/or age data, and patients of different genders and ages have different physical qualities, the diagnosis difficulty of the same disease of the patients of different genders and ages is different. Therefore, the doctor who is determined to be the patient to see the doctor is determined according to the symptom data set and the feature data set of the patient, the personal features such as symptoms and physical quality of the patient can be comprehensively considered, the doctor which is more suitable for the patient can be matched for the patient from multiple dimensions, and therefore the accuracy of matching the doctor for the patient can be improved, and further the cure rate of the patient and the medical experience of the patient are improved.
Optionally, the feature data set further comprises one or more of: occupational data, medical insurance data, economic competence data, treatment preference data, and drug preference data. The occupation data is used to reflect the patient's occupation. The medical insurance data is used for reflecting medical insurance application range, medical insurance reimbursement limit and other medical insurance conditions of the patient. The economic capability data is used to reflect the economic condition of the patient. The treatment preference data is used to reflect treatment modalities that are more acceptable to the patient. For example, treatment preference data may be used to reflect that a patient is more receptive to a more aggressive treatment modality, or treatment preference data may be used to reflect that a patient is more receptive to a more conservative treatment modality. The drug preference data is used to reflect the price and type of drug that is more acceptable to the patient.
In an optional implementation, before determining, from the doctor-patient matching coefficients of the patient and each candidate doctor, a target doctor for the patient to visit among the candidate doctors, the electronic device may further determine disease information indicating a target disease suffered by the patient according to the symptom data set. And acquiring the adequacy index of each candidate doctor on the target disease, wherein the adequacy index is used for reflecting the cure capacity of the target disease. And updating the doctor-patient matching coefficient of the patient and any candidate doctor according to the adequacy index of any candidate doctor on the target disease.
In another optional implementation manner, before determining, among a plurality of candidate doctors, a target doctor for the patient to see according to the doctor-patient matching coefficient of the patient and each candidate doctor, the electronic device may further obtain a workload coefficient of each candidate doctor, where the workload coefficient of any candidate doctor is used to reflect the number of visits of any candidate doctor in the current matching period. And updating the doctor-patient matching coefficient of the patient and any candidate doctor according to the workload coefficient of any candidate doctor.
In yet another optional implementation manner, before determining, by the electronic device, a target doctor for a patient to visit among the plurality of candidate doctors according to the doctor-patient matching coefficient of the patient and each candidate doctor, the electronic device may further obtain a waiting duration coefficient of each candidate doctor, where the waiting duration coefficient of any candidate doctor is used to reflect a waiting duration of the patient waiting for a visit of any candidate doctor. And updating the doctor-patient matching coefficient of the patient and any candidate doctor according to the waiting time coefficient of any candidate doctor.
In this application, the process of determining, by the electronic device, a target doctor for the patient to visit among the candidate doctors according to the doctor-patient matching coefficient between the patient and each candidate doctor may include: the electronic device filters one or more reservable doctors with the reserved number smaller than a first number threshold value from a plurality of candidate doctors. The electronic equipment determines the appointment-able doctor belonging to the largest doctor-patient matching coefficient as the target doctor in the doctor-patient matching coefficients of the patient and each appointment-able doctor in one or more appointment-able doctors.
Wherein the reserved number of the candidate doctors is the number of the patients which are determined to be seen by the candidate doctors. The first person threshold is the rated number of patients that can be seen by each candidate doctor (i.e. the upper limit number of persons that can be reserved). When the target doctor is determined according to the doctor-patient matching coefficient of the patient and each reservable doctor, the doctor-patient matching coefficient can be the updated doctor-patient matching coefficient or the non-updated doctor-patient matching coefficient. When the target doctor is determined by adopting the updated doctor-patient matching coefficient, more factors beneficial to the visit of the target doctor are considered in comparison with the non-updated doctor-patient matching coefficient, so that the target doctor can be determined more accurately according to the updated doctor-patient matching coefficient, and the matching accuracy of the patient and the doctor is improved.
Optionally, after the one or more reservable doctors with the reserved number smaller than the first number threshold are screened from the plurality of candidate doctors, the electronic device may further screen the reservable doctors, and the screened reservable doctors are doctors with the second benefit index larger than the benefit index threshold. Illustratively, the benefit index threshold may be a minimum second benefit index of the prospective physician acceptable to the patient, the minimum second benefit index reflecting the minimum level of excellence of the prospective physician in the target condition of the patient. Because the adequacy degree of each reservable doctor to the target disease of the patient is greater than the lowest adequacy degree after the rescreening, the target doctor is determined from the reservable doctors after the rescreening, the treatment effect of the target doctor can be ensured, and the matching accuracy of the patient and the target doctor is further improved.
In this application, the process of determining, by the electronic device, a target doctor for the patient to visit from among the candidate doctors according to the doctor-patient matching coefficient between the patient and each candidate doctor may further include: the electronic equipment determines the candidate doctor to which the maximum matching coefficient belongs as the target candidate doctor in the matching coefficients of the patient and each candidate doctor in the plurality of candidate doctors. And when the total number of the reserved patients in the current matching period of the target candidate doctor is equal to the second number threshold, if the benefit index of the target candidate doctor on the patient is greater than the minimum benefit index of the benefit indexes of the target candidate doctor on all the reserved patients of the target candidate doctor, the electronic equipment determines the target candidate doctor as the target doctor and updates the reserved patient to which the minimum benefit index belongs to the patient to be matched. The patient to be matched is a patient for which a doctor is not determined to visit, the benefit index of any target candidate doctor for any patient is obtained according to the excellence index of any target candidate doctor for any patient, and the excellence index of any target candidate doctor for any patient is used for reflecting the cure capability of any target candidate doctor for any patient.
Optionally, before the electronic device determines the target candidate doctor as the target doctor, the electronic device may further determine whether a patient matching coefficient of the patient with the target candidate doctor is greater than a matching coefficient threshold. The matching coefficient threshold may be a minimum value of doctor-patient matching coefficients acceptable to the patient. When the patient-patient matching coefficient of the patient and the target candidate doctor is smaller than the matching coefficient threshold value, which indicates that the patient cannot accept the matching degree of the patient and the corresponding target candidate doctor, the target candidate doctor is not determined as the target doctor. At this time, the electronic device may delete the target candidate doctor from the plurality of candidate doctors, and perform the above-described process of determining as the target doctor for the patient visit with respect to the remaining candidate doctors.
And after the target candidate doctor is determined as the target doctor, if the total number of the reserved patients in the current matching period of the target candidate doctor is equal to the second number threshold and the benefit index of the target candidate doctor for the patient is less than the minimum benefit index of the benefit indexes of the target candidate doctor for all the reserved patients of the target candidate doctor, the electronic equipment deletes the target candidate doctor from the candidate doctors, and executes the process of determining the target doctor as the patient for seeing diagnosis for the rest candidate doctors.
In a second aspect, a doctor matching apparatus for a patient is provided. The patient-specific doctor matching device comprises a plurality of functional modules, and the functional modules interact with each other to realize the method in the first aspect and the embodiments thereof. The functional modules may be implemented based on software, hardware or a combination of software and hardware, and the functional modules may be arbitrarily combined or divided based on specific implementations.
In a third aspect, a computer device is provided. The computer device includes: a processor and a memory. A memory for storing a computer program, the computer program comprising program instructions. And a processor, configured to invoke a computer program to implement the method in the first aspect and the embodiments thereof.
In a fourth aspect, a computer storage medium is provided. The computer storage medium has stored thereon instructions that, when executed by a processor, implement the method of the first aspect and its embodiments described above.
In a fifth aspect, a chip is provided, where the chip includes programmable logic circuits and/or program instructions, and when the chip runs, the method in the first aspect and its embodiments is implemented.
The beneficial effect that technical scheme that this application provided brought includes at least:
and directly determining the doctor-patient matching coefficient determined according to the symptom data set and the characteristic data set of the patient as the target doctor for the patient to see. And the feature data set for determining the doctor-patient matching coefficient comprises gender and age, but the diagnosis difficulty of different patients suffering from the same disease is different when the physical qualities of the different patients are different. When different patients have different treatment preferences and economic states, the matching degree and the treatment experience of the patients are different in the process of seeing the patients by doctors, so that the diagnosis effect of the diseases suffered by different patients can be different. Therefore, the doctor who is determined to be the patient to see the doctor is determined according to the symptom data set and the feature data set of the patient, the symptoms of the patient and personal features of the patient, such as physical quality, medical preference and economic state, can be comprehensively considered, and the doctor which is more suitable for the patient can be matched for the patient from multiple dimensions, so that the accuracy of matching the doctor for the patient can be improved, and the cure rate of the patient and the medical experience of the patient are improved.
Drawings
Fig. 1 is a schematic flowchart of a doctor matching method for a patient according to an embodiment of the present application;
FIG. 2 is a schematic probability diagram of an ATM provided by an embodiment of the present application;
FIG. 3 is a schematic flow chart illustrating a method for determining a target physician according to an embodiment of the present disclosure;
FIG. 4 is a schematic flow chart of another target doctor determination method provided in the embodiments of the present application;
FIG. 5 is a schematic structural diagram of a patient-specific physician-matching apparatus provided in an embodiment of the present application;
FIG. 6 is a schematic structural diagram of another patient-specific physician-matching apparatus provided in an embodiment of the present application;
fig. 7 is a block diagram of a computer device according to an embodiment of the present application.
Detailed Description
To make the objects, technical solutions and advantages of the present application more clear, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.
The embodiment of the application provides a doctor matching method for a patient, and the method can be applied to electronic equipment, such as a terminal and the like, wherein the terminal can be a computer, a personal computer, a medical intelligent terminal, a portable mobile terminal, a multimedia player, an electronic book reader, a wearable device and the like. The electronic equipment acquires a symptom data set and a feature data set of a patient, determines a doctor-patient matching coefficient of the patient and each candidate doctor in a plurality of candidate doctors, determines a target doctor for the patient to see according to the doctor-patient matching coefficient, and outputs indication information for indicating the target doctor. Wherein the symptom data set is used for reflecting the abnormal state of the body of the patient caused by the disease. The feature data set is used to identify personal features of the patient such as physical fitness, medical preferences, and economic status. And the physical quality of the patient can be identified using at least gender and/or age, i.e. the set of characteristic data comprises at least gender data and/or age data. Because different patients have different physical qualities, the difficulty of seeing the same disease is different among different patients. Further, the feature data set may also include occupational data, medical insurance data, economic competence data, treatment preference data, and drug preference data. When the personal characteristics such as the doctor preference, the economic state and the like of different patients are different, the matching degree and the doctor feeling of the patients are different in the process of seeing a doctor by a doctor, so that the seeing effect of the diseases suffered by different patients can also be different. Therefore, the doctor who is used for the patient to see the doctor is determined according to the symptom data set and the feature data set of the patient, personal features of the patient, such as symptoms, physical quality, medical preference and economic state, can be comprehensively considered, and the doctor which is more suitable for the patient can be matched for the patient from multiple dimensions, so that the accuracy of matching the doctor for the patient can be improved, and further the cure rate of the patient and the medical experience of the patient are improved.
For example, infants and elderly people have a greater difficulty in visiting the same disease than young people. The difficulty of the visit of female patients is larger than that of male patients. Therefore, when determining the doctor for the patient to visit, the doctor who is skilled in treating the patient in the age group to which the infant belongs can be selected for the infant, the doctor who is skilled in treating the patient in the age group to which the old belongs can be selected for the old, and the doctor who is skilled in treating the patient in the age group to which the young belongs can be selected for the young, so that the doctors can perform targeted visit to the patients in different age groups, and therefore, the accuracy of matching the patients with the doctors is improved.
The embodiment of the application also provides the electronic equipment with the diagnosis guide appointment function. The electronic device may be installed with a referral appointment application that may provide a referral appointment service for the patient. Alternatively, the electronic device may provide a diagnosis guide appointment service for the patient at the webpage side. By executing the doctor matching method for the patient provided by the embodiment of the application, the electronic equipment can match the doctor for the patient and reserve the function of the doctor for the patient, namely, provide a diagnosis guide reservation service for the patient. Wherein, the diagnosis guide appointment service may include: at least one of an online referral appointment service and a field referral appointment service. The on-line diagnosis guide appointment service refers to a service for realizing diagnosis guide appointment of a patient through an electronic device held by the patient. The on-site diagnosis guide appointment service refers to a service for a patient to use electronic equipment provided by a medical institution to realize a diagnosis guide appointment in the medical institution.
Referring to fig. 1, a flow chart of a doctor matching method for a patient according to an embodiment of the present application is shown. The method can be applied to electronic devices. The method comprises the following steps:
step 101, acquiring a symptom data set and a characteristic data set of a patient.
The symptom data set is used to reflect an abnormal state of the patient's body as a result of the disease. Each symptom data set includes one or more symptom data, each symptom data representing a symptom. Different symptom data sets are divided according to different patients, and different symptom data are divided according to different symptoms. For example, the symptom data set includes three symptom data of headache, fever, and edema of lower limbs. The feature data set (also called a scenario data set) is used to identify personal features such as physical fitness, medical preferences, and economic status of the patient. Each feature data set includes one or more feature data, each feature data representing a characteristic of the individual. Different feature data sets are divided according to different patients, and different feature data are divided according to different personal features. Wherein, in the characteristic data set, the physical quality of the patient can be identified by using at least gender and/or age, i.e. the characteristic data set comprises at least gender data and/or age data.
Optionally, the feature data set further comprises one or more of the following feature data: occupational data, medical insurance data, economic competence data, treatment preference data, and drug preference data. The occupation data is used to reflect the patient's occupation. The medical insurance data is used for reflecting medical insurance application range, medical insurance reimbursement limit and other medical insurance conditions of the patient. For example, the medical insurance data may include data reflecting the applicable range of medical insurance such as medical insurance in city, provincial medical insurance and commercial medical insurance, and data reflecting the reimbursement limit of 70% or 80% of the reimbursement proportion of medical insurance. The economic capability data is used to reflect the economic condition of the patient. For example, the economic capability data may reflect that the patient annual income is in a first interval (e.g., 5-10 tens of thousands (w) -10w), a second interval (e.g., 10-30 w), a third interval (e.g., 30-50 w), a fourth interval (e.g., 50-70 w), and so on. Wherein, the larger the interval value of the intervals such as the first interval, the second interval, the third interval and the fourth interval, the better the economic condition of the patient. The treatment preference data is used to reflect treatment modalities that are more acceptable to the patient. For example, treatment preference data may be used to reflect that a patient is more receptive to a more aggressive treatment modality, or treatment preference data may be used to reflect that a patient is more receptive to a more conservative treatment modality. Wherein, the aggressive treatment mode refers to a treatment mode with short treatment period, remarkable effect and slightly large side effect. A conservative treatment regime is one in which the treatment period is longer and the effect is slow, but the side effects are somewhat less. The drug preference data is used to reflect the price and type of drug that is more acceptable to the patient. For example, the drug preference data may include data reflecting that the patient is more likely to accept a more expensive drug price, or reflecting that the patient is more likely to accept a more economical drug price, or the like, reflecting that the patient is more likely to accept a more acceptable drug price range, and the drug preference data may also reflect that the patient is more likely to accept a traditional Chinese medicine, a western medicine, a traditional Chinese medicine, or the like. Wherein, for the medicine for treating the same disease, when the price of the medicine is larger than the specified price threshold value, the price of the medicine can be considered to be expensive; when the price of the drug is less than or equal to the specified price threshold, the drug price may be considered economical. And the specified price threshold may be determined according to application requirements.
Illustratively, the symptom data set may be headache, fever, and edema of the lower extremities. The feature data set may include: the sex mark male, the age mark 35, the occupation of the patient as the driver, the medical insurance condition of the patient as a medical insurance, the annual income of the patient in the interval of 5w-10w, the patient is easy to receive conservative treatment mode and economical medicine price.
And step 102, determining a doctor-patient matching coefficient of the patient and each candidate doctor in the candidate doctors according to the symptom data set and the characteristic data set.
The doctor-patient matching coefficient is used for reflecting the matching degree of the patient and the candidate doctor. The plurality of candidate doctors may be part or all of doctors in the medical institution, or may be part or all of doctors in each department of the medical institution, which is not limited in the embodiment of the present application.
In the embodiment of the present application, the electronic device may determine, according to the symptom data set and the feature data set, a doctor-patient matching coefficient between the patient and each of the candidate doctors in the plurality of candidate doctors in a plurality of ways, and the following two ways are taken as examples in the embodiment of the present application for explanation.
In a first optional implementation manner, according to a target symptom data set and a target feature data set of a target patient to be matched with a target doctor, a target disease suffered by the target patient is determined, a first probability of seeing the target disease by each candidate doctor is respectively determined, a second probability of seeing the patient with the target feature data set by each candidate doctor is determined, a third probability of occurrence of symptoms described by the target symptom data set when the patient with the target feature data set suffers from the target disease is determined, and then according to the first probability, the second probability and the third probability, a doctor-patient matching coefficient of the target patient and each candidate doctor is determined.
In order to distinguish the patient, the characteristic data set and the symptom data set involved in determining the first probability, the second probability and the third probability, the patient to be matched with the doctor is called a target patient, the symptom data set input by the patient is called a target symptom data set, and the characteristic data set is called a target characteristic data set. The electronic device is pre-stored with a first corresponding relation of a first probability of each candidate doctor seeing and diagnosing each disease in different diseases, a second corresponding relation of a second probability of each candidate doctor seeing and diagnosing a patient with each feature data in different feature data, and a third corresponding relation of a third probability of symptoms described by each symptom data in different symptom data when the patient with any feature data in different feature data suffers from any disease in different diseases. Therefore, the electronic device may query the first corresponding relationship, the second corresponding relationship, and the third corresponding relationship according to the target characteristic data of the target disease, so as to obtain a first probability corresponding to the target disease, a second probability corresponding to the target characteristic data, and a third probability corresponding to the target disease and the target characteristic data.
And, the first corresponding relationship, the second corresponding relationship and the third corresponding relationship may be obtained by a statistical or big data processing technique. For example, the first probability, the second probability and the third probability may be obtained by performing statistical or big data processing on a plurality of training documents, and each training document may record a candidate doctor data, and disease information of at least one disease visited by the candidate doctor, a feature data set and a symptom data set of at least one patient visited by the candidate doctor. Wherein the training document may be derived from a historical visit record of the medical facility.
Optionally, a plurality of training documents are obtained in advance, each training document corresponds to one candidate doctor, and disease information of one or more diseases visited by any candidate doctor, a feature data set and a symptom data set of one or more patients visited are recorded in the training document corresponding to any candidate doctor. The first probability, the second probability and the third probability are respectively counted according to the contents recorded in the plurality of training documents. The statistical modes of the first probability, the second probability and the third probability are respectively as follows:
the statistical mode of the first probability is as follows: and counting a first total number of times that any candidate doctor sees any one or more diseases and a second total number of times that any candidate doctor sees any one disease, and determining the ratio of the first total number of times to the second total number of times as a first probability that any candidate doctor sees any one disease. And sequentially counting the first probability that all candidate doctors visit the clinic to have diseases according to the statistical mode to obtain the first corresponding relation.
The statistical mode of the second probability is as follows: and counting a first total number of the feature data appearing when any candidate doctor looks at and a second total number of any feature data appearing in the process of looking at by any candidate doctor, and determining a ratio of the second total number to the first total number as a second probability of any feature data appearing when any candidate doctor looks at. And sequentially counting the second probabilities of all the characteristic data appearing when all the candidate doctors see the doctor according to the statistical mode to obtain the second corresponding relation.
The statistical mode of the third probability is as follows: and counting a first total number of patients with any disease and any characteristic data and any symptom data of the patients with any disease, which are diagnosed by any candidate doctor, and a second total number of patients with any characteristic data, which are diagnosed by all candidate doctors, and determining a ratio of the second total number to the first total number as a third probability of any characteristic data appearing when any candidate doctor is diagnosed. And sequentially counting the third probabilities of all the feature data appearing when all the candidate doctors see according to the statistical mode to obtain the second corresponding relation.
For each symptom data: first, a plurality of feature data corresponding to any candidate doctor is determined for the candidate doctor according to the second correspondence relationship (also called feature data distribution), and one feature data is selected from the plurality of feature data. For any candidate doctor, a plurality of pieces of disease information corresponding to the candidate doctor are determined based on the first correspondence relationship (also referred to as disease information distribution), and one piece of disease information is selected from the plurality of pieces of disease information. And determining a plurality of symptom data corresponding to the selected disease information and the selected feature data according to the selected disease information, the selected feature data and the third corresponding relationship (also called symptom data distribution), selecting one symptom data from the plurality of symptom data, and generating a data set of any one candidate doctor according to the selected disease information, the selected feature data and the symptom data. According to the mode, different symptom data are selected from the plurality of disease data for any candidate doctor aiming at different characteristic data and different disease information respectively, then one data set is generated according to the disease information, the characteristic data and the symptom data selected each time, and a plurality of data sets of any candidate doctor are obtained. Wherein, each data set is recorded with the corresponding relation of any candidate doctor, the selected disease information, the selected characteristic data and the symptom data. The process of generating a data set is then performed for each candidate doctor of the plurality of candidate doctors, resulting in a data set for each candidate doctor.
When a training document includes m symptom data and p feature data, since the symptom data and the feature data have m × p combination modes, in order to perform statistics on different symptom data and different feature data, respectively, p-1 symptom data may be copied, so that m × p symptom data after copying, each symptom data and one feature data form a disease feature set, thereby obtaining m × p disease feature sets, and performing statistics according to each disease feature set.
Optionally, the electronic device can determine doctor-patient matching coefficients of the patient with each candidate doctor using a doctor-patient matching model. The doctor-patient matching model stores a first corresponding relation, a second corresponding relation and a third corresponding relation. After the doctor-patient matching model receives the target symptom data set and the target characteristic data set of the target patient, according to the target symptom data set, the target feature data set, the first corresponding relation, the second corresponding relation and the third corresponding relation, a first probability that any candidate doctor visits the target disease determined by each target feature data in the target symptom data set, a second probability that each target feature data in the target feature data set appears when any candidate doctor visits the target disease, and the target feature data in the target feature data set are determined, and a third probability of having the target condition data of the target symptom data set in the patient having the target disease, and determining the doctor-patient matching coefficient of the target patient and any candidate doctor according to the determined first probability, second probability and third probability so as to obtain the doctor-patient matching coefficient of the patient and each candidate doctor.
Illustratively, the doctor-patient matching model may be an author-topic model (ATM). Fig. 2 is a schematic probability diagram of an ATM according to an embodiment of the present application. As shown in FIG. 2, x represents a candidate doctor, z represents disease information (also called a subject), s represents symptom data, and f representsiRepresenting characteristic data, theta representing disease information distribution, pi representing characteristic data distribution,
Figure BDA0002377686400000071
Indicating the distribution of symptom data, alpha is Dirichlet (Dirichlet) prior probability value of disease information distribution, beta is Dirichlet prior probability value of characteristic data distribution, gamma is Dirichlet prior probability value of symptom data distribution, A indicates the number of candidate doctors, K indicates the number of disease information, F indicates the number of characteristic data, D indicates the number of training documents, N indicates the number of symptom data in one training document, and B indicates the total number of types of symptom data in all the training documents. Where α, β, and γ are generally preset values.
Wherein, theta,
Figure BDA0002377686400000072
And π can be obtained according to the Gibbs sampling (Gibbs sampling) method. For example:
a candidate doctor x corresponds to a first probability of disease information z:
Figure BDA0002377686400000073
nx，zindicates the total number of training documents in which the information of the candidate doctor x and the disease information z are recorded,
Figure BDA0002377686400000074
the total number of training documents describing the information of this candidate doctor x and any disease information zi that all candidate doctors see.
One candidate doctor x corresponds to one feature data fiSecond probability of (2):
Figure BDA0002377686400000075
Figure BDA0002377686400000076
the candidate doctor x and the feature data f are shown and describediThe total number of training documents in the set of training documents,
Figure BDA0002377686400000077
the representation describes the total number of training documents that recorded candidate doctor x and any feature data that occurred when all candidate doctors looked at.
A set of disease features (z, f)i) Third probability corresponding to one symptom data s:
Figure BDA0002377686400000078
Figure BDA0002377686400000079
the expression shows the disease feature set (z, f)i) The total number of the symptom data s described,
Figure BDA00023776864000000710
the expression is recorded with a disease feature set (z, f)i) The total number of all symptom data that appear when all candidate physicians visit in the training document of (1).
Optionally, the doctor-patient matching coefficient of the target patient and any candidate doctor is positively correlated with the first probability, the second probability and the third probability corresponding to any candidate doctor. For example, the first probability, the second probability and the third probability corresponding to any candidate doctor, and the doctor-patient matching coefficient (probability) G of the target patient and any candidate doctor x satisfy:
Figure BDA00023776864000000711
wherein con represents a target feature data set of the target patient, the target feature data set comprising one or more feature data; sym represents a target symptom data set of the target patient, the target feature data set including one or more feature data; a ∈ b indicates that a is proportional to b;
Figure BDA0002377686400000081
denotes b1The product to bn.
In the embodiment of the application, after the doctor-patient matching coefficients of the target patient and each candidate doctor are determined, the electronic device may further perform normalization processing on the probabilities of the target patient and each candidate doctor to obtain normalized doctor-patient matching coefficients of the target patient and each candidate doctor, and then generate a doctor-patient matching list of the target patient according to the normalized doctor-patient matching coefficients of the target patient and each candidate doctor.
In a second optional implementation manner, the electronic device stores a doctor-patient correspondence in advance, and after receiving the target feature data set and the target symptom data set of the target patient, the electronic device may query the doctor-patient correspondence according to the target feature data set and the target symptom data set, so as to obtain a doctor-patient matching coefficient between the target patient and each candidate doctor. The doctor-patient corresponding relation records the corresponding relation between the characteristic data set and the symptom data set and the doctor-patient matching coefficient.
The doctor-patient corresponding relation can be stored in the electronic equipment in advance, and the doctor-patient corresponding relation can be established according to historical characteristic data sets and symptom data sets of a medical institution and doctor-patient matching coefficients determined according to each characteristic data set and each symptom data set.
And step 103, acquiring other parameter data.
Optionally, the electronic device may further update the doctor-patient matching coefficient with reference to other parameter data, and match the patient with a target doctor for the patient to see according to the updated doctor-patient matching coefficient, so as to improve accuracy of determining the target doctor. The implementation manner can be various, and it is described below:
optionally, the other parameter data comprises one or more of: the adequacy index of the candidate doctor on the target disease, the workload coefficient of the candidate doctor, the waiting time coefficient of the candidate doctor and the like.
Wherein the physician's adequacy index of the candidate for the target disease is used to reflect the physician's ability to cure the target disease, which is the disease the patient is suffering from. The waiting time length coefficient of the candidate doctor is used for reflecting the waiting time length of the patient waiting for the candidate doctor to see, and can also be used for reflecting the waiting speed of the patient waiting for the candidate doctor to see. The workload coefficient of the candidate doctor is used for reflecting the number of visits of the candidate doctor in the current matching period. When the electronic equipment provides the on-line appointment diagnosis guide service, the matching period is an output period for outputting instruction information indicating a target doctor to a patient, and the number of visits in the current matching period is the number of appointment visits in the current matching period. For example, if it is assumed that the electronic device provides an on-line diagnosis guide appointment service, the patient can appoint a doctor 3 days in advance, and the patient can receive the instruction information on the appointment day (i.e. the output period is 1 day), the matching period can be determined to be 1 day. When the electronic device provides the on-site diagnosis-guiding appointment service, the current matching period is the sum of the total duration of the doctor appointment made by the patient using the electronic device provided by the medical institution, and the number of the visits in the current matching period is the total number of the patients who can make the appointment using the electronic device provided by the medical institution. The duration of the current matching period may be determined according to application requirements. Illustratively, the current matching period may be 12 hours, one day, two days, seven days, or the like.
Optionally, parameter data such as the adequacy index of any candidate doctor for any disease, the workload coefficient of any candidate doctor, the waiting duration coefficient of any candidate doctor and the like can be obtained by adopting a calculation mode. The following explains the calculation manner of parameter data such as the adequacy index of any candidate doctor for any disease, the workload coefficient of any candidate doctor, and the waiting duration coefficient of any candidate doctor:
the process by which the electronic device calculates the adequacy index of any candidate physician for the target ailment may include: the electronic equipment firstly determines disease information used for indicating a target disease suffered by a target patient according to a symptom data set of the target patient; and then calculating the adequacy index of each candidate doctor for the target disease according to the reference factors.
Alternatively, the electronic device may store a knowledge map in advance, and the knowledge map is used for recording the correspondence between the symptom data and the disease information. The electronic device queries the knowledge-graph according to the symptom data set of the target patient to determine disease information reflecting the target disease corresponding to the symptom data set.
The reference factors include one or more of: sex factor, age factor, treatment regimen selection factor, drug selection factor, and the like. The examples of the present application are described with reference to four factors including a sex factor, an age factor, a treatment regimen selection factor, and a drug selection factor. At this time, any candidate doctor j has a good index e for the target disease of the target patient iijSatisfies the following conditions:
Figure BDA0002377686400000091
wherein,
Figure BDA0002377686400000092
represents the ratio of the proportion of patients having the same sex as the target patient i among all patients having any disease cured by any candidate doctor j to the proportion of patients having the same sex as the target patient i among all patients having the target disease. For example, when the target patient is a male patient,
Figure BDA0002377686400000093
Figure BDA0002377686400000094
represents the proportion of male patients in all patients with any disease cured by any candidate doctor j,
Figure BDA0002377686400000095
represents the proportion of male patients among all patients with the target disease.
Figure BDA0002377686400000096
Represents the ratio of the proportion of patients within the target age group of the target patient i to the proportion of patients within the target age group of all patients with the target disease who are cured by the candidate doctor j.
Figure BDA0002377686400000097
Represents the ratio of the proportion of patients having the same treatment preference as the target patient i among all patients having any disease cured by any candidate doctor j to the proportion of patients having the same treatment preference as the target patient i among all patients having the target disease.
Figure BDA0002377686400000098
All patients with any disease who showed cure by any candidate doctor j, and the target patienti the ratio of the proportion of patients with the same drug preference to the proportion of patients with the same drug preference as the target patient i, of all patients with the target disease.
It should be noted that the electronic device may store a default value of the reference factor, and if the electronic device does not acquire the feature data set of the target patient related to the reference factor, the electronic device may calculate the adequacy index of any candidate doctor for the target disease according to the default value of the corresponding reference factor.
The process by which the electronic device calculates the workload coefficients for any of the candidate physicians may include: and the electronic equipment calculates the workload coefficient of any candidate doctor according to the average number of the multiple candidate doctors in the current matching period and the number of the candidate doctors in the current matching period.
Optionally, the workload coefficient w for any candidate doctor jijSatisfies the following conditions:
Figure BDA0002377686400000099
wherein f isjThe number of visits for any candidate doctor j in the current matching period,
Figure BDA00023776864000000910
the average number of visits during the current matching period for a plurality of candidate doctors.
Alternatively, since the number of visits by each candidate physician over a fixed length of time is generally a fixed value, fjAnd
Figure BDA00023776864000000911
the value of (a) is also typically constant, and the constant can be obtained empirically. Therefore, the workload coefficient of any candidate doctor is also usually a fixed value, and in the embodiment of the present application, the electronic device may directly obtain the fixed value when performing step 103, without monitoring the number of visits of each candidate doctor in the plurality of candidate doctors in real time or performing calculation, so as to ensure that the number of visits of each candidate doctor is obtainedAnd under the condition of obtaining the workload coefficient of the candidate doctor, the calculation amount of the electronic equipment is reduced, and the calculation expense is reduced.
The process of calculating the waiting time coefficient of any candidate doctor for the target disease by the electronic device may include: the electronic device can calculate the waiting time coefficient of any candidate doctor according to the number of the patients who have reserved any candidate doctor and have not seen the doctor.
Optionally, the waiting time coefficient s of any candidate doctorijSatisfies the following conditions:
Figure BDA0002377686400000101
wherein h isjThe number of patients who have booked any of the candidate doctors j and have not yet seen a diagnosis. Wherein when sijWhen 1, it can be determined that none of the candidate physicians currently has an unviewed patient.
And step 104, updating the doctor-patient matching coefficient of the patient and each candidate doctor according to the other parameter data.
Optionally, when parameters included in other parameter data are different, the implementation manner of updating the doctor-patient matching coefficient according to the other parameter data is different, and the following seven optional implementation manners are taken as examples in the embodiment of the present application for description.
A first alternative implementation: when the other parameter data is the adequacy index of the candidate doctor on the target disease, the doctor-patient matching coefficient of the patient and any candidate doctor can be updated according to the adequacy index of any candidate doctor on the target disease.
Optionally, the doctor-patient matching coefficient determined in step 102 may be used as a first benefit index, the doctor-candidate excellence index for the target disease may be used as a second benefit index, and the updated doctor-patient matching coefficient may be represented by two-dimensional data including the first benefit index and the second benefit index. Alternatively, the doctor-patient matching coefficients for the patient and any of the candidate doctors are updated to be the product of the doctor-patient matching coefficients and the candidate doctor's index of excellence in the target disease.
A second alternative implementation: when the other parameter data is the workload coefficient of the candidate doctor, the doctor-patient matching coefficient of the patient and any candidate doctor can be updated according to the workload coefficient of any candidate doctor.
Optionally, the doctor-patient matching coefficient determined in step 102 may be used as a first benefit index, the workload coefficient of the candidate doctor may be used as a second benefit index, and the updated doctor-patient matching coefficient may be represented by two-dimensional data including the first benefit index and the second benefit index. Or updating the doctor-patient matching coefficient of the patient and any candidate doctor to be the product of the doctor-patient matching coefficient and the workload coefficient of the candidate doctor.
A third alternative implementation: when the other parameter data is the waiting time coefficient of the candidate doctor, the doctor-patient matching coefficient of the patient and any candidate doctor can be updated according to the waiting time coefficient of any candidate doctor. At this time, the updated doctor-patient matching coefficient may also be referred to as a first benefit index.
Optionally, the product of the waiting time coefficient and the doctor-patient matching coefficient of any candidate doctor can be used as a first benefit index, and the first benefit index is determined as the updated doctor-patient matching coefficient.
A fourth alternative implementation: when the other parameter data are the target disease adequacy index of the candidate doctor and the workload coefficient of the candidate doctor, the doctor-patient matching coefficient of the patient and any candidate doctor can be updated according to the target disease adequacy index of the candidate doctor and the workload coefficient of the candidate doctor.
Optionally, the doctor-patient matching coefficient determined in step 102 may be used as a first benefit index, the product of the candidate doctor's excellence index for the target disease and the candidate doctor's workload coefficient may be used as a second benefit index, and the updated doctor-patient matching coefficient may be represented by two-dimensional data including the first benefit index and the second benefit index.
A fifth alternative implementation: when the other parameter data are the adequacy index of the candidate doctor on the target disease and the waiting duration coefficient of the candidate doctor, the doctor-patient matching coefficient of the patient and any candidate doctor can be updated according to the adequacy index of the candidate doctor on the target disease and the waiting duration coefficient of the candidate doctor.
Optionally, the product of the doctor-patient matching coefficient determined in step 102 and the waiting time coefficient of the candidate doctor may be used as a first benefit index, the excellence index of the candidate doctor on the target disease may be used as a second benefit index, and the updated doctor-patient matching coefficient may be represented by using two-dimensional data including the first benefit index and the second benefit index.
A sixth alternative implementation: when the other parameter data are the workload coefficient of the candidate doctor and the waiting time length coefficient of the candidate doctor, the doctor-patient matching coefficient of the patient and any candidate doctor can be updated according to the workload coefficient of the candidate doctor and the waiting time length coefficient of the candidate doctor.
Optionally, the product of the doctor-patient matching coefficient determined in step 102 and the waiting time coefficient of the candidate doctor may be used as a first benefit index, the workload coefficient of the candidate doctor may be used as a second benefit index, and the updated doctor-patient matching coefficient may be represented by two-dimensional data including the first benefit index and the second benefit index.
A seventh optional implementation: when the other parameter data are the adequacy index of the candidate doctor on the target disease, the workload coefficient of the candidate doctor and the waiting duration coefficient of the candidate doctor, the doctor-patient matching coefficient of the patient and any candidate doctor can be updated according to the adequacy index of the candidate doctor on the target disease, the workload coefficient of the candidate doctor and the waiting duration coefficient of the candidate doctor.
Optionally, the product of the doctor-patient matching coefficient determined in step 102 and the waiting time coefficient of the candidate doctor may be used as a first benefit index, the product of the workload coefficient of the candidate doctor and the excellence index of the candidate doctor for the target disease may be used as a second benefit index, and the updated doctor-patient matching coefficient may be represented by using two-dimensional data including the first benefit index and the second benefit index.
Or, the process of updating the doctor-patient matching coefficient of the patient and any candidate doctor according to the adequacy index of the candidate doctor on the target disease, the workload coefficient of the candidate doctor and the waiting duration coefficient of the candidate doctor may further include: and determining the updated doctor-patient matching coefficient according to the product of the waiting duration coefficient, the doctor-patient matching coefficient, the excellence index for the target disease and the workload coefficient of any candidate doctor.
It should be noted that the above steps 103 and 104 are optional steps, and the steps 103 and 104 may be selected to be executed or not executed in the process of matching doctors for patients.
And step 105, determining a target doctor for the patient to see according to the doctor-patient matching coefficient of the patient and each candidate doctor in the plurality of candidate doctors.
Optionally, the electronic device may have multiple implementations of the process of determining the target doctor for the patient to visit among multiple candidate doctors according to the doctor-patient matching coefficient of the patient and each candidate doctor, and the following two optional implementations are exemplified in the embodiment of the present application.
A first alternative implementation, as shown in fig. 3, may be to determine the target physician among the reservable physicians. The implementation process can include:
step 1051a, the electronic device filters one or more reservable doctors with the reserved number smaller than a first number threshold from a plurality of candidate doctors.
Wherein the reserved number of the candidate doctors is the number of the patients which are determined to be seen by the candidate doctors. The first person threshold is the rated number of patients that can be seen by each candidate doctor (i.e. the upper limit number of persons that can be reserved). The implementation mode can be suitable for on-line diagnosis guide appointment service and on-site diagnosis guide appointment service. The first-person threshold used in the on-line diagnosis guide reservation service may be the same as or different from the first-person threshold used in the on-site diagnosis guide reservation service.
Step 1052a, the electronic device determines, as the target doctor, an appointment doctor to which the largest doctor-patient matching coefficient belongs, among the doctor-patient matching coefficients of the patient and each of the one or more appointment doctors.
When step 103 and step 104 are executed, when the target doctor is determined according to the doctor-patient matching coefficient of the patient and each reservable doctor, the doctor-patient matching coefficient is the updated doctor-patient matching coefficient. When step 103 and step 104 are not performed, the doctor-patient matching coefficient is the doctor-patient matching coefficient determined in step 102. When the target doctor is determined by adopting the updated doctor-patient matching coefficient, more factors beneficial to the visit of the target doctor are considered in comparison with the non-updated doctor-patient matching coefficient, so that the target doctor can be determined more accurately according to the updated doctor-patient matching coefficient, and the matching accuracy of the patient and the doctor is improved. And, when the updated doctor-patient matching coefficient is represented by two-dimensional data including a first benefit index and a second benefit index, the doctor-patient matching coefficient used in the first implementable manner of this step 105 is the first benefit index.
In this embodiment, after the electronic device performs the step 1051a, the electronic device may further screen a reservable doctor, and the screened reservable doctor is a doctor with a second benefit index greater than the benefit index threshold. Illustratively, the benefit index threshold may be a minimum second benefit index of the prospective physician acceptable to the patient, the minimum second benefit index reflecting the minimum level of excellence of the prospective physician in the target condition of the patient. Because the adequacy degree of each reservable doctor to the target disease of the patient is greater than the lowest adequacy degree after the rescreening, the target doctor is determined from the reservable doctors after the rescreening, the treatment effect of the target doctor can be ensured, and the matching accuracy of the patient and the target doctor is further improved.
Optionally, a benefit index threshold may be stored in the electronic device, and the benefit index threshold may be determined according to application requirements. Alternatively, the electronic device may calculate the benefit index threshold according to the parameter. For example, the benefit index threshold for any candidate physician j, when calculated from the parameters
Figure BDA0002377686400000121
Satisfies the following conditions:
Figure BDA0002377686400000122
wherein,
Figure BDA0002377686400000123
the second benefit index which is the smallest average among a plurality of candidate doctors (e.g., departments). That is to say are
Figure BDA0002377686400000124
n is a positive integer, and n is a positive integer,
Figure BDA0002377686400000125
the minimum value of the plurality of historical second benefit indexes of the No. r candidate doctor in the n candidate doctors where the appointment doctor is located is r is [1, n]Is a positive integer of (1).
α is a correction factor, which can be obtained based on the arrival rate of the prospective physician and/or whether the disease is in high-incidence stage. For example, the lower the arrival rate of the prospective doctor, the lower the correction factor; conversely, the higher the arrival rate of the prescheduled doctor, the higher the correction factor. Or when the target doctor is determined, if the disease which can be reserved and is adept to see by the doctor is in a high-incidence stage, the correction coefficient is lower; on the contrary, if the disease which the doctor can reserve to see is not in the high-incidence stage, the correction coefficient is higher.
For example, when the electronic device is implemented to provide the on-site diagnosis-guiding reservation service for the patient, if the target doctor is determined by using the first optional implementation manner, the first number threshold in step 1051a may be a first number of patients that can be seen by each candidate doctor in the on-site diagnosis-guiding reservation service provided by the electronic device, or may be a total number of patients that can be seen by each candidate doctor, where the total number is a sum of the number of patients that can be seen by each candidate doctor in the on-site diagnosis-guiding reservation service and the on-line diagnosis-guiding reservation service provided by the electronic device. Accordingly, if the first person count threshold is the first person count, the reserved number of candidate doctors is the number of patients who reserve doctors through the on-site diagnosis-guidance reservation service provided by the electronic device. If the first person number threshold value is the total number of the patients that can be seen by each candidate doctor, the reserved number of the candidate doctors is the number of all the patients that are determined to be seen by the candidate doctor. Optionally, the doctor-patient matching coefficient of the patient in the step 1052a and each of the one or more reservable doctors may be the doctor-patient matching coefficient updated in the third optional implementation manner in the step 104.
A second alternative implementation, as shown in fig. 4, may be to determine a target physician for a patient visit among a plurality of candidate physicians according to the first benefit index and the second benefit index. The implementation process can include:
and 1051b, determining the candidate doctor belonging to the maximum doctor-patient matching coefficient as the target candidate doctor in the doctor-patient matching coefficients of the patient and each candidate doctor in the candidate doctors.
Step 1052b, when the total number of the reserved patients in the current matching period of the target candidate doctor is equal to the second population threshold, if the benefit index of the target candidate doctor on the patient is greater than the minimum benefit index of the benefit indexes of the target candidate doctor on all the reserved patients of the target candidate doctor, determining the target candidate doctor as the target doctor, and updating the reserved patient to which the minimum benefit index belongs to the patient to be matched.
Wherein, the patient to be matched is a patient who is not determined to visit a doctor. And the benefit index of any target candidate doctor to any patient is obtained according to the excellence index of any target candidate doctor to any patient. In one implementation, the benefit index for any target candidate physician for any patient may be the excellence index for any target candidate physician for that patient. In another implementation, the benefit index for any target candidate physician for any patient may be the product of any target candidate physician's excellence index for any patient and any target candidate physician's workload factor. The second threshold number of people may be the same or different than the first threshold number of people.
Alternatively, when the total number of reserved patients of the target candidate doctor in the current matching period is less than the second number threshold, indicating that the target candidate doctor can accept the reservation of the patient, the electronic device may determine that the target candidate doctor is the target doctor.
In this embodiment, before performing step 1052b, the electronic device may further determine whether a doctor-patient matching coefficient (i.e., the maximum doctor-patient matching coefficient) of the patient and the target candidate doctor is greater than a matching coefficient threshold. The matching coefficient threshold may be a minimum value of doctor-patient matching coefficients acceptable to the patient. When the patient-patient matching coefficient of the patient and the target candidate doctor is smaller than the matching coefficient threshold value, which indicates that the patient cannot accept the matching degree of the patient and the corresponding target candidate doctor, the target candidate doctor is not determined as the target doctor. At this time, the electronic device may delete the target candidate doctor from the plurality of candidate doctors, and perform the above-described steps 1051b and 1052b for the remaining candidate doctors.
And, after executing step 1052b, when the total number of the reserved patients of the target candidate doctor in the current matching period is equal to the second population threshold, and the benefit index of the target candidate doctor for the patient is less than the minimum benefit index of the benefit indexes of the target candidate doctor for all the reserved patients of the target candidate doctor, deleting the target candidate doctor from the plurality of candidate doctors, and executing the above-mentioned steps 1051b and steps 1052b for the remaining candidate doctors.
For example, in the embodiment of the present application, the doctor-patient matching coefficient of the patient and each candidate doctor of the plurality of candidate doctors is the doctor-patient matching coefficient (i.e. the first benefit index) updated in the third optional implementation manner in step 103, and the benefit index is the second benefit index, which is used as an example, and the process of determining the target doctor by using the second optional implementation manner is described again.
Suppose that doctor d is included in the plurality of candidate doctors1And doctor d2Patient u1Patient u2And patient u3And patient u2And patient u3Ordered doctor d1. Doctor d1Has a first benefit index of L1For patient u1Has a benefit index of M1For patient u2Has a benefit index of M2And to patient u3Has a benefit index of M3(ii) a Doctor d2Has a first benefit index of L2For patient u1Has a benefit index of M4For patient u2Has a benefit index of M5And to patient u3Has a benefit index of M6. The matching coefficient threshold is L, and L1>L2>L3>L，M1>M2>M3>M4>M5>M6。
Determined as patient u1The process of visiting the target doctor comprises the following steps: the electronic equipment has a first benefit index L1First benefit index L2And a first benefit index L3In, the maximum benefit index L1The candidate doctor belongs to is determined as the target candidate doctor. And determining a first benefit index L1Greater than the matching coefficient threshold L. Get doctor d1When the total number U of the reserved patients in the current matching period is equal to the second number threshold value, the doctor d is acquired1Of an ordered patient u2Efficiency index M2And patient u3Efficiency index M3Medium minimum benefit index M3Due to doctor d1For patient u1Efficiency index M1Greater than doctor d1For patient u3Efficiency index M3Determining the target candidate doctor as the target doctor, and determining the minimum benefit index M3To the patient u3Updated to the patient to be matched, the patient u3The procedure of determining the target physician to visit the patient may continue.
If L is1>L2>L3>L is changed into L1>L>L2>L3The electronic device then determines a maximum first benefit index L1Then, due to the first benefit index L1If the matching coefficient is less than the threshold value L of the matching coefficient, the electronic equipment will obtain the maximum first benefit index L1The candidate doctors are deleted from the plurality of candidate doctors, and the process of determining the target doctor for the patient to see is executed for the rest candidate doctors, which is not redundant in the embodiment of the applicationThe above-mentioned processes are described.
And 106, outputting indication information for indicating the target doctor to see the patient.
The electronic device may have a display screen for displaying the indication information. After determining the target doctor, the electronic device may display the target doctor in a display screen to prompt the patient for the target doctor to visit for the patient.
Alternatively, the electronic device may periodically output the indication information. For example, the electronic device may output, to the patient, instruction information for instructing the target doctor to visit the patient after the end of one matching period. Taking the example in the step 1052b as an example, if the matching period is 1 day, the electronic device may also output instruction information for instructing the target doctor to visit the patient every day.
In the embodiment of the application, after the electronic device outputs the indication information for indicating the target doctor to visit the patient, the doctor matched with the patient is not changed.
In summary, the doctor-patient matching method for the patient provided by the embodiment of the present application directly determines the target doctor for the patient to see through the doctor-patient matching coefficient determined according to the symptom data set and the feature data set of the patient. And the feature data set for determining the doctor-patient matching coefficient comprises gender and age, but the diagnosis difficulty of different patients suffering from the same disease is different when the physical qualities of the different patients are different. When different patients have different treatment preferences and economic states, the matching degree and the treatment experience of the patients are different in the process of seeing the patients by doctors, so that the diagnosis effect of the diseases suffered by different patients can be different. Therefore, the doctor who is determined to be the patient to see the doctor is determined according to the symptom data set and the feature data set of the patient, the symptoms of the patient and personal features of the patient, such as physical quality, medical preference and economic state, can be comprehensively considered, and the doctor which is more suitable for the patient can be matched for the patient from multiple dimensions, so that the accuracy of matching the doctor for the patient can be improved, and the cure rate of the patient and the medical experience of the patient are improved.
By electronic equipmentThe method for realizing the on-line diagnosis guide appointment service is taken as an example, and the doctor matching method for the patient provided by the embodiment of the application is explained. Example one, assume that during the current matching period, patient u1Patient u2And patient u3Doctor appointments are sequentially made. Including doctor d among the plurality of candidate doctors1Doctor d2And doctor d3. The threshold value of the matching coefficient is 10, and the threshold value of the second person number is 2.
Electronic device separately acquires patient u1Patient u2And patient u3A symptom data set and a feature data set. And respectively determining the doctor-patient matching coefficient of each patient i and each doctor j according to the symptom data set and the characteristic data set of each patient to obtain the doctor-patient matching coefficient mij.
According to the acquired doctor d respectively1Doctor d2And doctor d3The waiting time coefficient sij and the doctor-patient matching coefficient mij, and determining a first benefit index xij of the patient and each doctor.
According to the acquired doctor d respectively1Doctor d2And doctor d3And determining a second benefit index yij for the excellence index eij and the workload coefficient wij of the target disease.
According to the appointment time of the patient, firstly, the patient u is determined1The target doctor for visiting. The patient u1The process of determining the target physician includes: and determining the maximum benefit index Lmax1 in the first benefit index x11, the first benefit index x12 and the first benefit index x 13. If x11>x12>x13, determining the doctor d to which the first benefit index x11 belongs1Is a target candidate doctor. If the first benefit index x11 is greater than 10, get doctor d1The total number U of reserved patients in the current matching period is 0. Since U is less than the second threshold number of people, doctor d1Determined as patient u1The target doctor who visits, i.e. for patient u1Doctor d appointment1To the patient u1The output is used for indicating doctor d1The indication information of (1).
Then determined as patient u2The target doctor for visiting. The patient u2The process of determining the target physician includes: and determining the maximum benefit index Lmax2 in the first benefit index x21, the first benefit index x22 and the first benefit index x 23. If x21>x22>x23, determining the doctor d to which the first benefit index x21 belongs1Is a target candidate doctor. If the first benefit index x21 is greater than 10, acquiring doctor d1The total number U of reserved patients in the current matching period is 1. Since U is less than the second threshold number of people, doctor d1Determined as patient u2And for patient u2Doctor d appointment1And then output for instructing doctor d1For patient u2And (5) indication information of a visit.
Then determined as patient u3The target doctor for visiting. The patient u3The process of determining the target physician includes: the largest first benefit index Lmax3 of the first benefit index x31, the first benefit index x32 and the first benefit index x33 is determined. If x31>x32>x33, determining the doctor d to which the first benefit index x31 belongs1Is a target candidate doctor. If the first benefit index x31 is greater than 10, acquiring doctor d1The total number U of reserved patients in the current matching period is 2. Since U is equal to the second population threshold, a second benefit index y11 and a second benefit index y21 are obtained, and the second benefit index y11 is determined to be greater than the second benefit index y 21. If doctor d1For patient u3Has a third benefit index y31 greater than doctor d1To doctor d1For the ordered patient u2And patient u3The second benefit index y21, doctor d1Determined as patient u3The target doctor of (1), subject u2And updating the patient to be matched. If doctor d1For patient u3Is less than the third benefit index y31 of doctor d1To doctor d1For the ordered patient u2And patient u3The second benefit index y21, doctor d1Deleted from the plurality of candidate doctors and directed to the remaining candidate doctors (i.e., doctor d)2And doctor d3) A procedure is performed that identifies the target physician for the patient visit.
The above procedure of determining the target doctor is repeated until 3 patients each determine the target doctor for which a visit is made, that is, 3 patients each match the target doctor.
The doctor matching method for the patient provided by the embodiment of the present application is described below by taking an example in which the electronic device implements the on-site diagnosis guide reservation service by the above method. Example two, suppose patient u4A doctor appointment was made. Including doctor d among the plurality of candidate doctors1Doctor d2And doctor d3. Electronic device determining patient u4The first benefit index x4j and the second benefit index y4j associated with each doctor j, and the process of determining the first benefit index x4j and the second benefit index y4j may refer to example one above.
Electronic device is in doctor d1Doctor d2And doctor d3The doctor d with the reserved number smaller than the first number threshold is obtained by medium screening2And doctor d3. And doctor d2Second benefit index x42 and physician d3Are greater than the benefit index threshold value, x 43. If patient u4To doctor d2X42 is greater than patient u4To doctor d3The first benefit index x43, and the doctor d to which the first benefit index x42 belongs2Determined as the target doctor and patient u4Doctor d appointment2And output for indicating doctor d2For patient u4And (5) indication information of a visit.
Fig. 5 is a schematic structural diagram of a doctor matching device for a patient according to an embodiment of the present application. As shown in fig. 5, the doctor matching apparatus 200 for a patient includes:
the first acquiring module 201 is configured to acquire a symptom data set and a feature data set of a patient, where the symptom data set is used to reflect an abnormal state of a body of the patient due to a disease, the feature data set is used to identify the patient, and the feature data set includes gender data and age data.
The first determining module 202 is configured to determine, according to the symptom data set and the feature data set, a doctor-patient matching coefficient of the patient and each candidate doctor of the plurality of candidate doctors, where the doctor-patient matching coefficient is used to reflect a degree of matching between the patient and the candidate doctor.
And the second determination module 203 is used for determining a target doctor for the patient to visit from the plurality of candidate doctors according to the doctor-patient matching coefficient of the patient and each candidate doctor.
And the output module 204 is used for outputting instruction information for instructing the target doctor to visit the patient.
Optionally, the feature data set further comprises one or more of: occupational data, medical insurance data, economic competence data, treatment preference data, and drug preference data.
Optionally, as shown in fig. 6, the doctor matching apparatus 200 for a patient further includes:
a third determining module 205 for determining disease information indicative of a target disease suffered by the patient based on the symptom data set.
A second obtaining module 206, configured to obtain a adequacy index of each candidate doctor for the target disease, where the adequacy index is used to reflect a capability of curing the target disease.
The first updating module 207 is used for updating the doctor-patient matching coefficient of the patient and any candidate doctor according to the excellence index of any candidate doctor on the target disease.
Optionally, the doctor matching apparatus 200 for a patient further includes:
and a third obtaining module 208, configured to obtain a workload coefficient of each candidate doctor, where the workload coefficient of any candidate doctor is used to reflect the number of visits of any candidate doctor in the current matching period.
And a second updating module 209, configured to update the doctor-patient matching coefficient between the patient and any candidate doctor according to the workload coefficient of any candidate doctor.
Optionally, the doctor matching apparatus 200 for a patient further includes:
the fourth obtaining module 210 is configured to obtain a waiting time length coefficient of each candidate doctor, where the waiting time length coefficient of any candidate doctor is used to reflect a waiting time length of a patient waiting for the patient to see the doctor.
And a third updating module 211, configured to update the doctor-patient matching coefficient between the patient and any candidate doctor according to the waiting duration coefficient of any candidate doctor.
Optionally, the second determining module 203 is configured to: and screening one or more reservable doctors with the reserved number smaller than the first number threshold value from a plurality of candidate doctors. And determining the appointment doctor to which the largest doctor-patient matching coefficient belongs as the target doctor in the doctor-patient matching coefficients of the patient and each appointment doctor in one or more appointment doctors.
Optionally, the second determining module 203 is configured to: and determining the candidate doctor to which the maximum matching coefficient belongs as the target candidate doctor in the matching coefficients of the patient and each candidate doctor in the plurality of candidate doctors.
When the total number of reserved patients in the current matching period of the target candidate doctors is equal to the second number threshold, if the benefit index of the target candidate doctors to the patients is larger than the minimum benefit index of the target candidate doctors to all the reserved patients of the target candidate doctors, the target candidate doctors are determined as the target doctors, the reserved patients to which the minimum benefit index belongs are updated to the patients to be matched, the patients to be matched are patients of which the visitors are not determined, the benefit index of any target candidate doctor to any patient is obtained according to the excellence index of any target candidate doctor to any patient, and the excellence index of any target candidate doctor to any patient is used for reflecting the cure capacity of any target candidate doctor to any patient on the diseases of any patient.
In summary, according to the doctor matching apparatus for a patient provided in the embodiment of the present application, the first determining module determines a doctor-patient matching coefficient according to the symptom data set and the feature data set of the patient acquired by the first acquiring module, and the second determining module directly determines a target doctor for the patient to see according to the doctor-patient matching coefficient. And the feature data set for determining the doctor-patient matching coefficient comprises gender and age, but the diagnosis difficulty of different patients suffering from the same disease is different when the physical qualities of the different patients are different. When different patients have different treatment preferences and economic states, the matching degree and the treatment experience of the patients are different in the process of seeing the patients by doctors, so that the diagnosis effect of the diseases suffered by different patients can be different. Therefore, the doctor who is determined to be the patient to see the doctor is determined according to the symptom data set and the feature data set of the patient, the symptoms of the patient and personal features of the patient, such as physical quality, medical preference and economic state, can be comprehensively considered, and the doctor which is more suitable for the patient can be matched for the patient from multiple dimensions, so that the accuracy of matching the doctor for the patient can be improved, and the cure rate of the patient and the medical experience of the patient are improved.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
Fig. 7 is a block diagram of a computer device according to an embodiment of the present application. As shown in fig. 7, computer device 300 may include a processor 301, a memory 302, a communication interface 303, and a bus 304. In the computer device, the number of the processors 301 may be one or more, and fig. 3 illustrates only one of the processors 301. Alternatively, the processor 301 may be a Central Processing Unit (CPU). If the computer device has multiple processors 301, the types of the multiple processors 301 may be different, or may be the same. Optionally, multiple processors of the computer device may also be integrated into a multi-core processor.
The memory 302 stores computer instructions and data, and the memory 302 may store the computer instructions and data needed to implement the patient-specific physician matching method provided herein. The memory 302 may be any one or any combination of the following storage media: nonvolatile memory (e.g., read-only memory (ROM), Solid State Disk (SSD), hard disk (HDD), optical disc, etc., volatile memory.
The communication interface 303 may be any one or any combination of the following devices: network interface (such as Ethernet interface), wireless network card, etc.
Communication interface 303 is used for data communication between the computer device and other nodes or other computer devices.
Fig. 3 also illustratively depicts bus 304. The bus 304 may connect the processor 301 with the memory 302 and the communication interface 303. Thus, via bus 304, processor 301 may access memory 302 and may also interact with other nodes or other computer devices using communication interface 303.
In the present application, a computer device executing computer instructions in the memory 302 may implement the patient-specific physician matching method provided herein. For example, execution of computer instructions in memory 302 by a computer device may perform the following steps: the method comprises the steps of obtaining a symptom data set and a characteristic data set of a patient, wherein the symptom data set is used for reflecting abnormal states of the body of the patient caused by diseases, the characteristic data set is used for identifying the patient, and the characteristic data set comprises gender data and age data. And determining a doctor-patient matching coefficient of the patient and each candidate doctor in the candidate doctors according to the symptom data set and the characteristic data set, wherein the doctor-patient matching coefficient is used for reflecting the matching degree of the patient and the candidate doctors. And determining a target doctor for the patient to visit from a plurality of candidate doctors according to the doctor-patient matching coefficient of the patient and each candidate doctor. And outputting indication information for indicating the target doctor to visit the patient. Moreover, the computer device executes the computer instructions in the memory 302, and accordingly, the implementation process of executing this step may refer to the corresponding description in the above method embodiments.
The embodiment of the application also provides a computer storage medium, wherein the computer storage medium is provided with instructions stored thereon, and the storage medium is a nonvolatile computer-readable storage medium, and when the instructions are executed by a processor, the doctor matching method for the patient provided by the embodiment of the application is realized.
Embodiments of the present application also provide a chip, which includes a programmable logic circuit and/or program instructions, and when the chip is operated, the chip is used to implement the doctor matching method for the patient provided by the embodiments of the present application.
Embodiments of the present application further provide a computer program product, which when run on an electronic device, causes the electronic device to execute the doctor matching method for a patient provided by embodiments of the present application.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
In the embodiments of the present application, the terms "first", "second", and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
The term "and/or" in this application is only one kind of association relationship describing the associated object, and means that there may be three kinds of relationships, for example, a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.
The above description is only exemplary of the present application and is not intended to limit the present application, and any modifications, equivalents, improvements, etc. made within the spirit and principles of the present application are intended to be included within the scope of the present application.

Claims (16)

1. A physician matching method for a patient, the method comprising:
acquiring a symptom data set and a characteristic data set of a patient, wherein the symptom data set is used for reflecting an abnormal state of the body of the patient caused by diseases, the characteristic data set is used for identifying the patient, and the characteristic data set comprises gender data and age data;
determining a doctor-patient matching coefficient of the patient and each candidate doctor in a plurality of candidate doctors according to the symptom data set and the feature data set, wherein the doctor-patient matching coefficient is used for reflecting the matching degree of the patient and the candidate doctors;
according to the doctor-patient matching coefficient of the patient and each candidate doctor, determining a target doctor for the patient to see in the plurality of candidate doctors;
outputting instruction information for instructing the target doctor to visit the patient.
2. The method of claim 1, wherein the feature data set further comprises one or more of: occupational data, medical insurance data, economic competence data, treatment preference data, and drug preference data.
3. The method of claim 1 or 2, wherein before determining, among the plurality of candidate physicians, a target physician for the patient to visit based on the patient-to-patient matching coefficients for each candidate physician, the method further comprises:
determining disease information indicative of a target disease suffered by the patient from the symptom data set;
obtaining a adequacy index of each candidate physician for the target disease, the adequacy index reflecting the ability to cure the target disease;
updating doctor-patient matching coefficients of the patient and any candidate doctor according to the excellence index of any candidate doctor on the target disease.
4. The method of any one of claims 1 to 3, wherein before determining, among the plurality of candidate physicians, a target physician for the patient to visit based on the doctor-patient matching coefficients of the patient with each candidate physician, the method further comprises:
acquiring a workload coefficient of each candidate doctor, wherein the workload coefficient of any candidate doctor is used for reflecting the number of visits of any candidate doctor in the current matching period;
and updating the doctor-patient matching coefficient of the patient and any candidate doctor according to the workload coefficient of any candidate doctor.
5. The method of any one of claims 1 to 4, wherein before determining, among the plurality of candidate physicians, a target physician for the patient to visit based on the doctor-patient matching coefficients of the patient with each candidate physician, the method further comprises:
acquiring a waiting time coefficient of each candidate doctor, wherein the waiting time coefficient of any candidate doctor is used for reflecting the waiting time of the patient waiting for the waiting of any candidate doctor;
and updating doctor-patient matching coefficients of the patient and any candidate doctor according to the waiting time coefficient of any candidate doctor.
6. The method according to any one of claims 1 to 5, wherein the determining, among the candidate doctors, a target doctor for the patient to visit according to the doctor-patient matching coefficient of the patient with each candidate doctor comprises:
screening one or more reservable doctors with the reserved number smaller than a first number threshold value from the plurality of candidate doctors;
and determining the appointment doctor to which the largest doctor-patient matching coefficient belongs as the target doctor in the doctor-patient matching coefficients of the patient and each appointment doctor in the one or more appointment doctors.
7. The method according to any one of claims 1 to 6, wherein the determining, among the candidate doctors, a target doctor for the patient to visit according to the doctor-patient matching coefficient of the patient with each candidate doctor comprises:
determining, among the matching coefficients of the patient and each candidate doctor of the plurality of candidate doctors, the candidate doctor to which the largest matching coefficient belongs as the target candidate doctor;
when the total number of reserved patients of the target candidate doctor in the current matching period is equal to the second number threshold, if the benefit index of the target candidate doctor for the patient is larger than the minimum benefit index of the benefit indexes of the target candidate doctor for all the reserved patients of the target candidate doctor, determining the target candidate doctor as the target doctor, updating the reserved patient to which the minimum benefit index belongs as a patient to be matched, the patient to be matched is a patient without a confirmed doctor, the benefit index of any target candidate doctor to any patient is obtained according to the excellence index of any target candidate doctor to any patient, the adequacy index of any target candidate doctor for any patient is used for reflecting the cure capability of any target candidate doctor for the disease suffered by any patient.
8. A physician-matched apparatus for a patient, the apparatus comprising:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring a symptom data set and a characteristic data set of a patient, the symptom data set is used for reflecting an abnormal state of the body of the patient caused by diseases, the characteristic data set is used for identifying the patient, and the characteristic data set comprises gender data and age data;
a first determination module, configured to determine, according to the symptom data set and the feature data set, a doctor-patient matching coefficient of the patient and each candidate doctor in a plurality of candidate doctors, where the doctor-patient matching coefficient is used to reflect a degree of matching between the patient and the candidate doctor;
a second determination module, configured to determine, from the doctor-patient matching coefficients of the patient and each candidate doctor, a target doctor for the patient to visit among the candidate doctors;
and the output module is used for outputting indication information for indicating the target doctor to see the patient.
9. The method of claim 8, wherein the feature data set further comprises one or more of: occupational data, medical insurance data, economic competence data, treatment preference data, and drug preference data.
10. The apparatus of claim 8 or 9, further comprising:
a third determination module for determining disease information indicative of a target disease suffered by the patient based on the symptom data set;
a second obtaining module for obtaining a adequacy index of each candidate doctor for the target disease, wherein the adequacy index is used for reflecting the cure capability of the target disease;
the first updating module is used for updating doctor-patient matching coefficients of the patient and any candidate doctor according to the excellence index of any candidate doctor on the target disease.
11. The apparatus of any one of claims 8 to 10, further comprising:
the third acquisition module is used for acquiring the workload coefficient of each candidate doctor, and the workload coefficient of any candidate doctor is used for reflecting the number of visits of any candidate doctor in the current matching period;
and the second updating module is used for updating the doctor-patient matching coefficient of the patient and any candidate doctor according to the workload coefficient of any candidate doctor.
12. The apparatus of any one of claims 8 to 11, further comprising:
the fourth acquisition module is used for acquiring the waiting time coefficient of each candidate doctor, and the waiting time coefficient of any candidate doctor is used for reflecting the waiting time of the patient waiting for the patient to see;
and the third updating module is used for updating the doctor-patient matching coefficient of the patient and any candidate doctor according to the waiting duration coefficient of any candidate doctor.
13. The apparatus of any of claims 8 to 12, wherein the second determining module is configured to:
screening one or more reservable doctors with the reserved number smaller than a first number threshold value from the plurality of candidate doctors;
and determining the appointment doctor to which the largest doctor-patient matching coefficient belongs as the target doctor in the doctor-patient matching coefficients of the patient and each appointment doctor in the one or more appointment doctors.
14. The apparatus of any of claims 8 to 13, wherein the second determining module is configured to:
determining, among the matching coefficients of the patient and each candidate doctor of the plurality of candidate doctors, the candidate doctor to which the largest matching coefficient belongs as the target candidate doctor;
when the total number of reserved patients of the target candidate doctor in the current matching period is equal to the second number threshold, if the benefit index of the target candidate doctor for the patient is larger than the minimum benefit index of the benefit indexes of the target candidate doctor for all the reserved patients of the target candidate doctor, determining the target candidate doctor as the target doctor, updating the reserved patient to which the minimum benefit index belongs as a patient to be matched, the patient to be matched is a patient without a confirmed doctor, the benefit index of any target candidate doctor to any patient is obtained according to the excellence index of any target candidate doctor to any patient, the adequacy index of any target candidate doctor for any patient is used for reflecting the cure capability of any target candidate doctor for the disease suffered by any patient.
15. A computer device, comprising: a processor and a memory;
the memory for storing a computer program, the computer program comprising program instructions;
the processor, for invoking the computer program, implementing the doctor matching method for a patient according to any one of claims 1 to 7.
16. A computer storage medium having stored thereon instructions which, when executed by a processor, carry out a doctor matching method for a patient according to any one of claims 1 to 7.
CN202010072681.8A 2020-01-21 2020-01-21 Doctor matching method and device for patient Pending CN113223677A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010072681.8A CN113223677A (en) 2020-01-21 2020-01-21 Doctor matching method and device for patient

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010072681.8A CN113223677A (en) 2020-01-21 2020-01-21 Doctor matching method and device for patient

Publications (1)

Publication Number Publication Date
CN113223677A true CN113223677A (en) 2021-08-06

Family

ID=77085408

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010072681.8A Pending CN113223677A (en) 2020-01-21 2020-01-21 Doctor matching method and device for patient

Country Status (1)

Country Link
CN (1) CN113223677A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113903442A (en) * 2021-10-19 2022-01-07 北京富通东方科技有限公司 Special doctor recommendation method and device
CN118173281A (en) * 2024-04-01 2024-06-11 首都体育学院 Method and equipment for recommending online doctor for patient

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113903442A (en) * 2021-10-19 2022-01-07 北京富通东方科技有限公司 Special doctor recommendation method and device
CN118173281A (en) * 2024-04-01 2024-06-11 首都体育学院 Method and equipment for recommending online doctor for patient

Similar Documents

Publication Publication Date Title
US11462308B2 (en) Triage routing based on inference data from computer vision model
US20190325995A1 (en) Method and system for predicting patient outcomes using multi-modal input with missing data modalities
US20190287684A1 (en) Medical system interface apparatus and methods to classify and provide medical data using artificial intelligence
US6061657A (en) Techniques for estimating charges of delivering healthcare services that take complicating factors into account
US11276495B2 (en) Systems and methods for predicting multiple health care outcomes
JP2018060529A (en) Method and apparatus of context-based patient similarity
JP2011520195A (en) Method and system for personalized guideline-based therapy augmented by imaging information
JP2014503894A (en) System and method for medical decision support for treatment planning using case-based reasoning
US10424403B2 (en) Adaptive medical documentation system
US20210151140A1 (en) Event Data Modelling
US20190318829A1 (en) Adaptive medical documentation system
US20210257067A1 (en) State transition prediction device, and device, method, and program for learning predictive model
KR101565331B1 (en) Analyzing system for medical informations using patterns and the method thereof
CN113223677A (en) Doctor matching method and device for patient
CN114783580B (en) Medical data quality evaluation method and system
CN109545384A (en) A kind of medical diagnostic method and device
CN114743625A (en) Electronic health record management method, system and computer storage medium
US20070055543A1 (en) Medical resource estimation and simulation system
US20200219617A1 (en) Apparatus and method for initial information gathering from patients at the point of care
CN112599227A (en) Hospital resource consumption control method and system, corresponding equipment and storage medium
US20150339602A1 (en) System and method for modeling health care costs
JP5729049B2 (en) Information management program, information management apparatus, and information management method
US20200075163A1 (en) Diagnostic decision support for patient management
US20130035959A1 (en) Methods and systems for tracking medical care
US20220189592A1 (en) Automated transformation documentation of medical data

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination